SimGRAG, as described by Cai et al. (2024), employs instruction fine-tuning for RAG with filtering using Llama-3-8B-Instruct and Gemma-2-27B-it models, utilizing Wikipedia and PubMed knowledge graphs for domain-specific and multi-choice QA tasks.

Authors

• Person: Not available Organization: arXiv
  Large Language Models Meet Knowledge Graphs for Question ...

Sources

• Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv via serper

Referenced by nodes (3)

• RAG concept
• PubMed concept
• Wikipedia concept